INDEX

Explanations

technical identifiers or codes, likely related to a programming context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 otomatig

-0.77

 ویکی‌پدیای

-0.77

(")");

-0.76

FunctionFlags

-0.74

 дописавши

-0.73

 itſelf

-0.73

StoryboardSegue

-0.73

LookAnd

-0.72

complexContent

-0.71

таратура

-0.70

POSITIVE LOGITS

1.21

0.86

0.70

 weiße

0.61

xid

0.61

xa

0.60

ｘ

0.58

ี้ย

0.58

х

0.57

×

0.56

Activations Density 0.218%

technical identifiers or codes, likely related to a programming context

No Comments

No Known Activations